Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 701 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.5307. Min Act: -0.1700

Data Index: 7577635 (Open Web Text)

Max Activating Token Index: 206

Text #1

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.5029. Min Act: -0.1700

Data Index: 751628 (Open Web Text)

Max Activating Token Index: 143

Text #2

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.4674. Min Act: -0.1700

Data Index: 6326323 (Open Web Text)

Max Activating Token Index: 359

Text #3

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.4658. Min Act: -0.1700

Data Index: 1426713 (Open Web Text)

Max Activating Token Index: 457

Text #4

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.4505. Min Act: -0.1700

Data Index: 5748878 (Open Web Text)

Max Activating Token Index: 238

Text #5

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3770. Min Act: -0.1700

Data Index: 3398364 (Open Web Text)

Max Activating Token Index: 773

Text #6

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3391. Min Act: -0.1700

Data Index: 6085762 (Open Web Text)

Max Activating Token Index: 432

Text #7

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.4217. Min Act: -0.1700

Data Index: 1273875 (Open Web Text)

Max Activating Token Index: 395

Text #8

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3420. Min Act: -0.1700

Data Index: 5505920 (Open Web Text)

Max Activating Token Index: 775

Text #9

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3674. Min Act: -0.1700

Data Index: 3659209 (Open Web Text)

Max Activating Token Index: 910

Text #10

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3697. Min Act: -0.1700

Data Index: 7734 (Open Web Text)

Max Activating Token Index: 777

Text #11

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3564. Min Act: -0.1700

Data Index: 7897986 (Open Web Text)

Max Activating Token Index: 517

Text #12

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3210. Min Act: -0.1700

Data Index: 8548740 (Open Web Text)

Max Activating Token Index: 483

Text #13

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3270. Min Act: -0.1700

Data Index: 946782 (Open Web Text)

Max Activating Token Index: 499

Text #14

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3094. Min Act: -0.1700

Data Index: 4617660 (Open Web Text)

Max Activating Token Index: 646

Text #15

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.2791. Min Act: -0.1700

Data Index: 7829308 (Open Web Text)

Max Activating Token Index: 519

Text #16

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3015. Min Act: -0.1700

Data Index: 2067689 (Open Web Text)

Max Activating Token Index: 863

Text #17

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3370. Min Act: -0.1700

Data Index: 1175717 (Open Web Text)

Max Activating Token Index: 456

Text #18

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.3036. Min Act: -0.1700

Data Index: 3337742 (Open Web Text)

Max Activating Token Index: 501

Text #19

Max Range: 3.5307. Min Range: -3.5307

Max Act: 3.2945. Min Act: -0.1700

Data Index: 2779448 (Open Web Text)

Max Activating Token Index: 769